The interconnectivities of built and natural environments can serve as conduits for the proliferation and dissemination of antibiotic resistance genes (ARGs), which in turn can result in human exposure and potential threats to public health. Several studies have compared the broad spectrum of ARGs (i.e., “resistomes”) in various environmental compartments and the human gut, but there is a need to identify unique ARG occurrence patterns (i.e., “discriminatory ARGs”) that are characteristic of each resistome. Such an approach will help identify factors influencing ARG proliferation, facilitate comparisons of the ARGs distinguishing various environments, and help pave the way towards ranking environments based on their likelihood of contributing to the spread of clinically relevant antibiotic resistance. Here we formulate and demonstrate an approach using an extremely randomized tree (ERT) algorithm combined with a Bayesian optimization technique to capture ARG variability in environmental samples and identify discriminatory ARGs. The approach was evaluated on both <i>in silico</i> metagenomic datasets and real metagenomic datasets. The approach was found to readily identify discriminatory ARGs in the <i>in silico</i> datasets. Analyses of real datasets further demonstrated that the ERT approach can effectively differentiate real-world samples and identify discriminatory ARGs based on pre-defined categorizing schemes. Furthermore, it is crucial to delineate the risk posed by resistomes on human health and link it with socio-economic risk factors. The analysis of sewage and human gut metagenomes from across the globe is underway. The objective is to build a machine learning model based on the World Bank’s health, nutrition and population data to predict the risk of these resistomes and identify important contributing socioeconomic risk factors. The study provides insight into key markers and metrics for mitigating the spread of antibiotic resistance.

Identification of discriminatory ARGs and socio-economic factors in shaping resistome risk using machine learning algorithms

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.